Hugging Face's logo

tien007
/
llama-3-8b-sft

Transformers
Safetensors
PyTorch
English
llama3
Inference Endpoints
Model card Files Community
llama-3-8b-sft / README.md
tien007's picture
tien007
Update README.md
cf4d04a verified
preview code
|
raw
history blame contribute delete
2.59 kB
metadata
library_name: transformers
tags:
  - pytorch
  - llama3
license: llama3
datasets:
  - ruslanmv/ai-medical-chatbot
language:
  - en
metrics:
  - accuracy

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

  • Developed by: ManhTien(Money)
  • Funded by: [More Information Needed]
  • Shared by : [More Information Needed]
  • Model type: natural language model - llm3
  • Language(s) (NLP): [More Information Needed]
  • License: [More Information Needed]
  • Finetuned from model: meta-llama/Meta-Llama-3.1-8B-Instruct

Usage

Here is an example of how to use the tien007/llama-3-8b-sft model with Hugging Face's Transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_id = "tien007/llama-3-8b-sft"
model = AutoModelForCausalLM.from_pretrained(model_id, ignore_mismatched_sizes=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Define input messages
messages = [{ "role": "user", "content": "How to effectively treat cancer?" }]

# Prepare the prompt
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# Tokenize input and move to GPU
inputs = tokenizer(prompt, return_tensors='pt', padding=True, truncation=True).to("cuda")

# Generate a response
outputs = model.generate(**inputs, max_length=150, num_return_sequences=1)

# Decode the response
text = tokenizer.decode(outputs[0], skip_special_tokens=True)

# Print the response
print(text.split("assistant")[1])

Recommendations

Results

Summary

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

  • Hardware Type: [More Information Needed]
  • Hours used: [More Information Needed]
  • Cloud Provider: [More Information Needed]
  • Compute Region: [More Information Needed]
  • Carbon Emitted: [More Information Needed]